Search

We propose a novel system leveraging deep learning-based methods to predict urban traffic accidents and estimate their severity. The major challenge is the data imbalance problem in traffic accident prediction. The problem is caused by numerous zero values in the dataset due to the rarity of traffic accidents. To address the issue, we propose a grid-clustered feature map with the ideas of grids and cells. To predict the occurrence of accidents in the grid, we introduce an accident detector that combines the power of a Convolutional Neural Network (CNN) with a Deep Neural Network (DNN). Then, hierarchical DNNs are supposed to be an accident risk classifier to estimate the risk of each cell in the accident-occurrence grid. The proposed system can effectively reduce instances with no traffic accidents. Furthermore, we introduce the concept of the Accident Risk Index (ARI) to better represent the severity of risk at each cell. Also, we consider all the explanatory variables, such as dangerous driving behaviors, traffic mobility, and safety facility information, that can be related to traffic accidents. To improve the prediction accuracy, we further take into consideration all the explanatory variables, such as dangerous driving behaviors, traffic mobility, and safety facility information, that can be related to traffic accidents. In the experiment, we highlight the benefits of our method for urban traffic accident management by significantly improving model performance compared to the baselines. The feasibility and applicability of the proposed system are validated in the data of Daejeon City, Republic of Korea. The proposed prediction system can dynamically advise and recommend commuters, traffic management systems, and city planners on alternatives, optimizations, and interventions. [ABSTRACT FROM AUTHOR]

Raoultella ornithinolytica is an Enterobacteriaceae bacterium that can infect both humans and animals, while luteolin-7-O-glucoside (IOG) is a flavonoid that has broad effects on the intestinal microbiota of healthy animals. However, current studies lack sufficient data on intestinal microbiota dysbiosis and drug resistance transmission caused by R. ornithinolytica and the possible role of IOG. In this study, BALB/c mice were infected with R. ornithinolytica carrying blaNDM-1 gene and treated with IOG (3 mg/kg·d and 6 mg/kg·d) to analyze the diversity of intestinal microbiota and the transfer of blaNDM-1 between bacteria. The findings indicated that R. ornithinolytica B1645-1 exhibited a significant ability to enhance the Firmicutes/Bacteroidota ratio and increase the relative abundance of Lactobacillus and Bacillus after 48 h, where as 6 mg/kg·d IOG had an opposite effect. Moreover, R. ornithinolytica B1645-1 facilitated the emergence of drug-resistant bacteria and promoted blaNDM-1 gene transfer in Enterococcus, Escherichia, Klebsiella, Acinetobacter, Bacillus, Brevibacterium, and Lactobacillus. Enterococcus was the predominant genus at 48 h. Surprisingly, 6 mg/kg·d IOG significantly inhibited the production of drug-resistant bacteria and promoted blaNDM-1 gene transfer from Enterococcus to Lactobacillus at 144 h. However, the role of Lactobacillus as a recipient for drug-resistant genes should be of more concern. [ABSTRACT FROM AUTHOR]

Background: Antibiotics exert an outstanding selective pressure on bacteria, forcing their chromosomal gene mutations and drug resistance genes to spread. The objective of this study is to evaluate the expression of the New Delhi Metallo-β-Lactamase-1 gene (blaNDM−1) in the clinical isolate (Klebsiella pneumoniae TH-P12158), transformant strains Escherichia coli BL21 (DE3)-blaNDM−1, and Escherichia coli DH5α- blaNDM−1 when exposed to imipenem. Methods: β-Lactamase genes (blaSHV, blaTEM−1, blaCTX−M−9, blaIMP, blaNDM−1, blaKPC, blaOXA, blaGES, and blaDHA) from randomly selected carbapenems-sensitive K.pneumoniae (n = 20) and E.coli (n = 20) strains were amplified by PCR. The recombinant plasmid of pET-28a harboring blaNDM−1 was transformed into E.coli BL21 (DE3) and E.coli DH5α by electroporation. The resistance phenotype and higher blaNDM−1 expression in K.pneumoniae TH-P12158, transformant E.coli BL21 (DE3)-blaNDM−1, and E.coli DH5α-blaNDM−1 were observed when exposed to imipenem with grade increasing, decreasing, and canceling doses, respectively. Results: After being exposed to different doses of imipenem, the minimum inhibitory concentration (MIC) and the minimum bactericidal concentration (MBC) of antimicrobial drugs and blaNDM−1 expression of strains increased, which was positively correlated with doses of imipenem. On the contrary, with the decrease or cancellation of imipenem doses, the blaNDM−1 expression was deteriorated, while the MIC and MBC values remained relatively stable. These results demonstrated that low doses of imipenem (˂MIC) could press blaNDM−1 positive strains producing stable drug resistance memory and altered blaNDM−1 expression. Conclusions: Low doses of imipenem could press blaNDM−1 positive strains producing sustained resistance memory and altered blaNDM−1 expression. In particular, the positive correlation between the resistance genes expression and antibiotics exposure shows promising guiding significance for clinical medication. [ABSTRACT FROM AUTHOR]